AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation

Young-Bum Kim, Sungjin Lee, Xinnuo Xu, Guoyin Wang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• XinnuoXu/AugNLG

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have over hundreds of intents and thousands of slots, neither template-based approaches nor model-based approaches are scalable. Recently, neural NLGs started leveraging transfer learning and showed promising results in few-shot settings. This paper proposes AUGNLG, a novel data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model, to automatically create MR-to-Text data from open-domain texts. The proposed system mostly outperforms the state-ofthe-art methods on the FEWSHOTWOZ data in both BLEU and Slot Error Rate. We further confirm improved results on the FEW-SHOTSGD data and provide comprehensive analysis results on key components of our system. Our code and data are available at https: //github.com/XinnuoXu/AugNLG. MR: inform_no_match (kidsallowed = yes) TEXT: I cannot find restaurants with kids allowed.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.05589")
get_code_for_paper("2106.05589")
have("2106.05589")

Connect an agent — have() is free.